INDEX

Explanations

temporal measurements and durations

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

énario

-0.71

oreille

-0.71

 /\.(

-0.57

 motherhood

-0.56

первых

-0.54

jší

-0.54

ųjų

-0.53

AutoSize

-0.53

migrationBuilder

-0.52

POSITIVE LOGITS

 months

1.27

 weeks

1.25

weeks

1.08

 Months

1.06

months

1.05

 years

1.00

 month

0.99

 MONTHS

0.98

 WEEKS

0.94

Months

0.90

Activations Density 0.261%

temporal measurements and durations

No Comments

No Known Activations